Agent skill

time-series-forecaster

Time series forecasting skill for business metric prediction and demand planning

View SKILL.md on GitHub Repository
Stars 514
Forks 31

Install this agent skill to your Project

npx add-skill https://github.com/a5c-ai/babysitter/tree/main/library/specializations/domains/business/decision-intelligence/skills/time-series-forecaster

Metadata

Additional technical details for this skill

domain
business
category
forecasting
priority
medium
specialization
decision-intelligence
tools libraries 
[
    "prophet",
    "statsforecast",
    "darts",
    "sktime",
    "nixtla"
]
shared candidate
YES

SKILL.md

Time Series Forecaster

Overview

The Time Series Forecaster skill provides comprehensive capabilities for predicting business metrics over time using classical statistical methods, machine learning, and deep learning approaches. It supports automated model selection, ensemble forecasting, and uncertainty quantification for robust business planning.

Capabilities

  • Classical methods (ARIMA, ETS, Theta)
  • Machine learning methods (XGBoost, LightGBM for time series)
  • Deep learning methods (Prophet, N-BEATS, Temporal Fusion Transformer)
  • Ensemble forecasting
  • Prediction interval generation
  • Forecast accuracy metrics (MAPE, RMSE, MASE)
  • Anomaly detection
  • Seasonality decomposition

Used By Processes

  • Predictive Analytics Implementation
  • KPI Framework Development
  • Market Sizing and Opportunity Assessment

Usage

Data Input

python
# Time series data configuration
time_series_data = {
    "target": "monthly_revenue",
    "datetime_column": "date",
    "frequency": "M",  # Monthly
    "data": [
        {"date": "2023-01-01", "value": 1000000, "marketing_spend": 50000},
        {"date": "2023-02-01", "value": 1050000, "marketing_spend": 55000},
        # ... more data
    ],
    "exogenous_variables": ["marketing_spend", "economic_index"],
    "special_events": [
        {"date": "2023-11-24", "event": "black_friday", "impact": "positive"},
        {"date": "2023-12-25", "event": "christmas", "impact": "mixed"}
    ]
}

Model Configuration

python
# Forecasting configuration
forecast_config = {
    "horizon": 12,  # 12 months ahead
    "models": {
        "auto_select": True,
        "candidates": ["arima", "ets", "prophet", "lightgbm"],
        "ensemble": {
            "method": "weighted_average",
            "weights": "based_on_cv_performance"
        }
    },
    "validation": {
        "method": "time_series_cv",
        "n_splits": 5,
        "test_size": 3
    },
    "prediction_intervals": [0.50, 0.80, 0.95]
}

Seasonality Analysis

python
# Seasonality decomposition
seasonality_config = {
    "method": "stl",  # or "classical", "x13"
    "seasonal_periods": [12],  # yearly for monthly data
    "robust": True,
    "output_components": ["trend", "seasonal", "residual"]
}

Model Selection Guide

Model Best For Handles
ARIMA Stationary data with autocorrelation Trend, AR/MA patterns
ETS Exponential patterns Trend, Seasonality, Error
Prophet Business time series Trend, Multiple seasonality, Holidays
Theta Simple forecasting Trend extrapolation
N-BEATS Complex patterns Non-linear trends, Interpretable
TFT Multi-horizon, multivariate Exogenous vars, Attention
XGBoost Feature-rich forecasting Exogenous variables

Accuracy Metrics

Metric Formula Use Case
MAPE Mean Absolute Percentage Error Scale-independent comparison
RMSE Root Mean Square Error Penalizes large errors
MASE Mean Absolute Scaled Error Compares to naive forecast
SMAPE Symmetric MAPE Handles near-zero values
Coverage % in prediction interval Calibration check

Input Schema

json
{
  "time_series": {
    "target": "string",
    "datetime_column": "string",
    "frequency": "string",
    "data": ["object"],
    "exogenous_variables": ["string"]
  },
  "forecast_config": {
    "horizon": "number",
    "models": "object",
    "validation": "object",
    "prediction_intervals": ["number"]
  },
  "analysis_options": {
    "decomposition": "boolean",
    "anomaly_detection": "boolean",
    "feature_importance": "boolean"
  }
}

Output Schema

json
{
  "forecasts": {
    "point_forecast": ["number"],
    "prediction_intervals": {
      "lower_80": ["number"],
      "upper_80": ["number"],
      "lower_95": ["number"],
      "upper_95": ["number"]
    },
    "dates": ["string"]
  },
  "model_performance": {
    "selected_model": "string",
    "cv_metrics": {
      "MAPE": "number",
      "RMSE": "number",
      "MASE": "number"
    },
    "all_models": "object"
  },
  "decomposition": {
    "trend": ["number"],
    "seasonal": ["number"],
    "residual": ["number"]
  },
  "anomalies": [
    {
      "date": "string",
      "value": "number",
      "expected": "number",
      "severity": "string"
    }
  ],
  "feature_importance": "object (if applicable)"
}

Best Practices

  1. Use at least 2-3 full seasonal cycles of historical data
  2. Check for and handle missing values appropriately
  3. Consider external factors (holidays, promotions, economic indicators)
  4. Validate with time series cross-validation (not random split)
  5. Report prediction intervals, not just point forecasts
  6. Monitor forecast accuracy over time and retrain as needed
  7. Be cautious with long-horizon forecasts (uncertainty compounds)

Integration Points

  • Feeds into KPI Tracker for forward-looking metrics
  • Connects with Monte Carlo Engine for scenario analysis
  • Supports Predictive Analyst agent
  • Integrates with Decision Visualization for forecast charts

Recommended Agent Skills

Expand your agent's capabilities with these related and highly-rated skills.

a5c-ai/babysitter

gsd-tools

Central utility skill for GSD operations. Provides config parsing, slug generation, timestamps, path operations, and orchestrates calls to other specialized skills. Acts as the unified entry point that the original gsd-tools.cjs provided via its lib/ modules (commands, config, core, init).

514 31
Explore
a5c-ai/babysitter

model-profile-resolution

Resolve model profile (quality/balanced/budget) at orchestration start and map agents to specific models. Enables cost/quality tradeoffs by selecting appropriate AI models for each agent role.

514 31
Explore
a5c-ai/babysitter

verification-suite

Plan structure validation, phase completeness checks, reference integrity verification, and artifact existence confirmation. Provides the structured verification layer ensuring GSD artifacts are well-formed and complete.

514 31
Explore
a5c-ai/babysitter

state-management

STATE.md reading, writing, and field-level updates. Provides cross-session state persistence via .planning/STATE.md with structured fields for current task, completed phases, blockers, decisions, and quick tasks.

514 31
Explore
a5c-ai/babysitter

git-integration

Git commit patterns, formats, and conventions for GSD methodology. Provides atomic commits per task, structured commit messages, planning file commits, branch management, and milestone tag operations.

514 31
Explore
a5c-ai/babysitter

frontmatter-parsing

YAML frontmatter parsing and manipulation for .planning/ documents. Provides read, write, update, query, and validation operations on frontmatter blocks in GSD markdown artifacts.

514 31
Explore

Didn't find tool you were looking for?

Be as detailed as possible for better results